郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！
Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.
Abstract
1. Introduction
2. Related Work
3. Method
3.1. Basic Loss Formulation
3.2. Bridge Task Gap: Decoupled Foreground and Background Decoding
3.3. Bridge Data Gap: Conditioned Mask Decoding
4. Experiment
4.1. Experimental Setup
4.2. Open-Vocabulary Benchmarking
4.3. Direct and Task-Specific Transfer
4.4. Segmentation and Detection in the Wild
4.5. Ablation
5. Conclusion